youtube-dl

commit: a373befa25bb521f94facb01c2cef45850c1e7c9
parent df63cafe497d7530d887786d5a54ca11bf5e73db
Author: Remita Amine <remitamine@gmail.com>
Date:   Tue, 24 Sep 2019 20:23:56 +0100

[nhk] fix video extraction(closes #22249)(closes #22353)

Diffstat:
M
youtube_dl/extractor/nhk.py
4
++--
M
youtube_dl/extractor/piksel.py
14
+++++++++++---

2 files changed, 13 insertions(+), 5 deletions(-)
diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py
@@ -60,8 +60,8 @@ class NhkVodIE(InfoExtractor):
         if is_video:
             info.update({
                 '_type': 'url_transparent',
-                'ie_key': 'Ooyala',
-                'url': 'ooyala:' + episode['vod_id'],
+                'ie_key': 'Piksel',
+                'url': 'https://player.piksel.com/v/refid/nhkworld/prefid/' + episode['vod_id'],
             })
         else:
             audio = episode['audio']
diff --git a/youtube_dl/extractor/piksel.py b/youtube_dl/extractor/piksel.py
@@ -15,7 +15,7 @@ from ..utils import (
 
 
 class PikselIE(InfoExtractor):
-    _VALID_URL = r'https?://player\.piksel\.com/v/(?P<id>[a-z0-9]+)'
+    _VALID_URL = r'https?://player\.piksel\.com/v/(?:refid/[^/]+/prefid/)?(?P<id>[a-z0-9_]+)'
     _TESTS = [
         {
             'url': 'http://player.piksel.com/v/ums2867l',
@@ -40,6 +40,11 @@ class PikselIE(InfoExtractor):
                 'timestamp': 1486171129,
                 'upload_date': '20170204'
             }
+        },
+        {
+            # https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2019240/
+            'url': 'http://player.piksel.com/v/refid/nhkworld/prefid/nw_vod_v_en_2019_240_20190823233000_02_1566873477',
+            'only_matching': True,
         }
     ]
 
@@ -52,8 +57,11 @@ class PikselIE(InfoExtractor):
             return mobj.group('url')
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_id = self._search_regex(
+            r'data-de-program-uuid=[\'"]([a-z0-9]+)',
+            webpage, 'program uuid', default=display_id)
         app_token = self._search_regex([
             r'clientAPI\s*:\s*"([^"]+)"',
             r'data-de-api-key\s*=\s*"([^"]+)"'